Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
Noisy Early Stopping for Noisy Labels
William Toner, Amos Storkey
Training neural network classifiers on datasets contaminated with noisy labels significantly increases the risk of overfitting. Thus, effectively implementing Early Stopping in noi…
cs.LG2023
Label Noise: Correcting the Forward-Correction
William Toner, Amos Storkey
Training neural network classifiers on datasets with label noise poses a risk of overfitting them to the noisy labels. To address this issue, researchers have explored alternative…